| title | Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions |
|---|---|
| authors | Xinnong Zhang, Wanting Shan, Hanjia Lyu, Zhongyu Wei, Jiebo Luo |
| date | 2026-06-04 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.06443 |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Large language models are increasingly used to simulate social media users and infer how individuals may respond to online discussions. However, it remains unclear whether these simulations reflect precise user-specific beliefs or whether they are highly sensitive to semantically independent changes in conversational contexts. In this work, we study counterfactual context revision as a framework for auditing LLM-based stance simulation. Given an original online conversation, we first infer a target user's stance toward a specific topic. We then apply controlled revision strategies to the conversational context and simulate the user's stance again under the revised context. We compare text-only revision strategies with a multimodal one that incorporates meme-based context and evaluate two main effectiveness metrics, i.e., average directional stance shift and stance transition rate. The results reveal effective and robust stance transitions in both text-only and multimodal strategies across different polarization-preference mechanisms. Our study contributes an evaluation framework for understanding the context sensitivity of LLM-based stance simulation. More broadly, it highlights both the promise and risk of using LLMs to simulate online opinion dynamics. |
cite
@misc{zhang2026revising,
title={Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions},
author={Xinnong Zhang and Wanting Shan and Hanjia Lyu and Zhongyu Wei and Jiebo Luo},
year={2026},
eprint={2606.06443},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.06443}
}